vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Host-memory leak on eager `reshape_and_cache_flash` path
- [Bug]: GLM 5.2; Garbled output with sequence-parallel MoE on small decode batches (TP+EP+DP)
- [Bugfix] Fix sequence-parallel detection for small decode batches
- [Model Support] Kimi K3 Tracking Issue
- [rocm] perf: drop redundant -inf prefill of decode paged MQA-logits buffer
- [DCP][Performance] Add Shared-DCP peer-addressable decode data paths
- [DCP][Kernel] Add Shared-DCP consumer-direct Top-K
- [Bug]: Sleep mode wake_up crashes EngineCore natively on DGX Spark (GB10, unified memory) — sleep level 1 works, wake kills the engine
- DSpark: num_speculative_tokens < dspark_block_size guard (from #47419) has no corresponding code path — should be a warning
- Chunked prefill paged decode masked load perf [ROCm] [bugfix]
- Docs
- Python not yet supported